moai-essentials-perf

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's code and documentation are focused on performance optimization. There is no evidence of malicious intent, credential theft, or unauthorized data exfiltration.\n- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the Scalene profiler using pip. Scalene is a reputable, well-known tool for CPU and memory profiling.\n- [COMMAND_EXECUTION]: The skill includes bash commands to install tools and run the profiler, which are standard operations within a performance tuning workflow.\n- [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill processes external files and web-based data.\n
  • Ingestion points: The process_csv_good function and fetchUserDataParallel function in examples.md ingest data from local CSV files and remote APIs respectively.\n
  • Boundary markers: The examples do not include delimiters or specific instructions to ignore embedded prompts in processed data.\n
  • Capability inventory: The skill is configured to use the Read, Bash, and WebFetch tools.\n
  • Sanitization: Content retrieved from external sources is processed without explicit sanitization or validation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 05:15 PM